together-deploy-integration

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external deployment manifests and Together AI documentation to determine deployment steps. This creates a potential surface where malformed documentation or manifests could attempt to influence the agent's behavior.
  • Ingestion points: Deployment manifests (referenced in Instructions), external Together AI documentation URLs (fetched via WebFetch).
  • Boundary markers: Not explicitly defined for the processing of external technical documentation.
  • Capability inventory: The skill uses Write and Edit tools to modify deployment configuration files based on the ingested instructions.
  • Sanitization: No explicit sanitization or validation logic for the content of the fetched documentation is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 06:10 PM
Security Audit — agent-trust-hub — together-deploy-integration